EMD-YOLO:一种基于改进YOLO11n的PCB缺陷检测模型

doi:10.16088/j.issn.1001-6600.2025121201

摘要/Abstract

摘要： 针对现有缺陷检测方法在小目标、复杂背景与不规则形态下边缘特征提取能力弱、多尺度感知不足及定位精度有限的问题,本文提出一种改进YOLO11n的PCB表面缺陷检测模型EMD-YOLO。该模型通过引入边缘增强模块(edge enhancement, EE)与多尺度边缘信息增强模块(multi-scale edge information, MSEI),提升对微小及复杂缺陷的边缘特征表征能力,并通过轻量级的多尺度池化构建特征金字塔,增强模型的多尺度感知能力。此外,本文在训练中采用DIoU损失函数优化边界框回归精度,进一步提高定位精度。实验结果表明,EMD-YOLO在PKU-Market PCB数据集上的平均检测精度(mAP@50)相比基线模型YOLOv11n提升3.8个百分点,并在计算复杂度几乎不变的情况下,显著提升模型的实用性与鲁棒性。

关键词: PCB, 缺陷检测, 计算机视觉, 损失函数, 多尺度特征融合

Abstract: To address the limitations of existing defect detection methods, namely weak edge feature extraction for small targets, inadequate multi-scale perception under complex backgrounds and irregular morphologies, and limited localization accuracy, an improved YOLO11n-based PCB surface defect detection model, termed EMD-YOLO, is proposed. An Edge Enhancement (EE) module and a Multi-Scale Edge Information Enhancement (MSEI) module are introduced to strengthen the representation of edge features for minute and structurally complex defects. Additionally, a lightweight multi-scale pooling scheme is employed to construct a feature pyramid, by which the network’s multi-scale perception capability is enhanced. Furthermore, the Distance-IoU (DIoU) loss function is adopted during training to optimize bounding box regression, by which localization accuracy is further improved. Experimental results on the PKU-Market PCB dataset demonstrate that a 3.8 percentage point improvement in mean average precision (mAP@50) is achieved by EMD-YOLO compared to the baseline YOLO11n model, while nearly unchanged computational complexity is maintained, thereby significantly enhancing the model’s practicality and robustness.

Key words: PCB, defect detection, computer vision, loss function, multi-scale feature fusion

中图分类号: TP391.41

索贵东, 陆志敏, 李自立. EMD-YOLO:一种基于改进YOLO11n的PCB缺陷检测模型[J]. 广西师范大学学报（自然科学版）, 2026, 44(5): 49-62.

Suo Guidong, Lu Zhimin, Li Zili. EMD-YOLO: a PCB defect detection model based on improved YOLO11n[J]. Journal of Guangxi Normal University(Natural Science Edition), 2026, 44(5): 49-62.

参考文献

[1] Wang F, Yue Z Y, Liu J Y, et al. Quantitative imaging of printed circuit board (PCB) delamination defects using laser-induced ultrasound scanning imaging[J]. Journal of Applied Physics, 2022, 131(5): 053101. DOI: 10.1063/5.0077766.
[2] Ding R W, Dai L H, Li G P, et al. TDD-net: a tiny defect detection network for printed circuit boards[J]. CAAI Transactions on Intelligence Technology, 2019, 4(2): 110-116. DOI: 10.1049/trit.2019.0019.
[3] Hecht O, Dishon G. Automatic optical inspection (AOI) of thin film multichip modules[C]//8th IEEE/CHMT International Conference on Electronic Manufacturing Technology Symposium. Piscataway, NJ: IEEE, 1990: 130-136. DOI: 10.1109/IEMT8.1990.171097.
[4] 黄璇. PCB元器件自动光学检测技术研究[J]. 华东科技, 2022(9): 51-53. DOI: 10.3969/j.issn.1006-8465.2022.09.017.
[5] 吴一全, 赵朗月, 苑玉彬, 等. 基于机器视觉的PCB缺陷检测算法研究现状及展望[J]. 仪器仪表学报, 2022, 43(8): 1-17. DOI: 10.19650/j.cnki.cjsi.J2209701.
[6] 刘志豪,李自立,苏珉.智能通信与无人机结合的YOLOv8电动车骑行者头盔佩戴检测方法[J].广西师范大学学报(自然科学版), 2026, 44(1): 23-32.DOI: 10.16088/j.issn.1001-6600.2025010101.
[7] 李娟. 基于机器学习的PCB缺陷检测与分类方法研究[J]. 印制电路信息, 2024, 32(3): 57-59. DOI: 10.3969/j.issn.1009-0096.2024.03.014.
[8] 文斌, 胡晖, 杨超. 基于LWN-Net的印刷电路板缺陷检测算法[J]. 计算机集成制造系统, 2024, 30(2): 496-507. DOI: 10.13196/j.cims.2022.0818.
[9] 王龙业, 黄鋆, 曾晓莉. 基于YOLO-PCB的印刷电路板裸板缺陷检测[J]. 科学技术与工程, 2024, 24(15): 6338-6345. DOI: 10.12404/j.issn.1671-1815.2304232.
[10] 沈萍, 李想, 杨宁, 等. 基于三重注意力的轻量级YOLOv8印刷电路板缺陷检测算法[J]. 微电子学与计算机, 2024, 41(4): 20-30. DOI: 10.19304/J.ISSN1000-7180.2023.0846.
[11] 胡兰兰, 邓超. 基于YOLO-MCG的PCB缺陷检测算法[J]. 仪表技术与传感器, 2024(4): 100-106. DOI: 10.3969/j.issn.1002-1841.2024.04.018.
[12] Lim J, Lim J, Baskaran V M, et al. A deep context learning based PCB defect detection model with anomalous trend alarming system[J]. Results in Engineering, 2023, 17: 100968. DOI: 10.1016/j.rineng.2023.100968.
[13] Xu Y Z, Wu H, Liu Y L, et al. PCB electronic component soldering defect detection using YOLO11 improved by retention block and neck structure[J]. Sensors, 2025, 25(11): 3550. DOI: 10.3390/s25113550.
[14] 黄文杰,罗维平,陈镇南,等.基于YOLO11的轻量化PCB缺陷检测算法研究[J].广西师范大学学报(自然科学版), 2026, 44(1): 56-67.DOI: 10.16088/j.issn.1001-6600.2025022502.
[15] 王彩霞, 郭鑫鹏, 刘鹏. 改进YOLOv8n的电路板缺陷检测算法[J]. 电子测量与仪器学报, 2025, 39(8): 65-78. DOI: 10.13382/j.jemi.B2508194.
[16] 毛剑. 基于YOLOV7蒸馏模型的道路缺陷检测算法研究[J]. 现代制造技术与装备, 2023, 59(2): 222-224. DOI: 10.16107/j.cnki.mmte.2023.0084.
[17] Chen Y J, Ding Y Y, Zhao F, et al. Surface defect detection methods for industrial products: a review[J]. Applied Sciences, 2021, 11(16): 7657. DOI: 10.3390/app11167657.
[18] Howard A G, Zhu M L, Chen B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications[PP/OL]. arXiv (2017-04-17)[2025-12-12].https://doi.org/10.48550/arXiv.1704.04861.
[19] Liu L, Ouyang W, Wang X G, et al. Deep learning for generic object detection: a survey[J]. International Journal of Computer Vision, 2020, 128(2): 261-318. DOI: 10.1007/s11263-019-01247-4.
[20] Li K, Wan G, Cheng G, et al. Object detection in optical remote sensing images: a survey and a new benchmark[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 159: 296-307. DOI: 10.1016/j.isprsjprs.2019.11.023.
[21] Lin T Y, Dollar P, Girshick R, et al. Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Los Alamitos, CA: IEEE Computer Society, 2017: 936-944. DOI: 10.1109/CVPR.2017.106.
[22] Zhou Y B, Yuan M H, Zhang J, et al. Review of vision-based defect detection research and its perspectives for printed circuit board[J]. Journal of Manufacturing Systems, 2023, 70: 557-578. DOI: 10.1016/j.jmsy.2023.08.019.
[23] Szegedy C, Liu W, Jia Y Q, et al. Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Los Alamitos, CA: IEEE Computer Society, 2015: 1-9. DOI: 10.1109/CVPR.2015.7298594.
[24] Zheng Z H, Wang P, Liu W, et al. Distance-IoU loss: faster and better learning for bounding box regression[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7): 12993-13000. DOI: 10.1609/aaai.v34i07.6999.
[25] 吴葛, 朱宇凡, 贾泽宁. 改进YOLO11的PCB表面缺陷检测方法[J]. 电子测量技术, 2025, 48(14): 136-145. DOI: 10.19651/j.cnki.emt.2518156.
[26] 杨彦萍, 高军伟, 刘兆龙, 等. 基于改进YOLO11的印刷电路板表面缺陷检测算法[J]. 液晶与显示, 2025, 40(10): 1545-1556.
[27] Liu C J, Zhang M X, Yan H W, et al. CSYOLO: a YOLOv8-based PCB defect detection model integratin composite backbone networks and dynamic snake convolution[J]. Journal of Measurement Science and Instrumentation, 2026, 17(1): 151-161.DOI: 10.62756/jmsi.1674-8042.2026013.
[28] 毛坤, 朱学军, 赖惠鸽, 等.多尺度融合优化的印刷电路板缺陷检测算法[J]. 激光与光电子学进展,2025, 62(10): 141-152. DOI: 10.3788/LOP250474.

相关文章 15

[1]	孙莹, 徐宝. 共轭先验分布下逆伽马分布尺度参数的Bayes分析[J]. 广西师范大学学报（自然科学版）, 2026, 44(5): 112-121.
[2]	王成龙, 宋强, 李文峰, 张仕民. PAM-DETR: 基于改进RT-DETR的医用手套小目标缺陷检测算法[J]. 广西师范大学学报（自然科学版）, 2026, 44(4): 79-95.
[3]	杨云波, 南新元, 蔡鑫. 基于改进YOLO11n的光伏板缺陷检测方法[J]. 广西师范大学学报（自然科学版）, 2026, 44(3): 47-59.
[4]	钱俊磊, 王熹之, 曾凯, 杜学强, 刘贺, 朱立光. 基于MHTD-YOLO11n的钢材表面缺陷检测算法[J]. 广西师范大学学报（自然科学版）, 2026, 44(3): 60-74.
[5]	毕桦男, 高丙朋, 蔡鑫. SOP-DETR:基于改进RT-DETR的海下垃圾检测算法[J]. 广西师范大学学报（自然科学版）, 2026, 44(3): 75-88.
[6]	吕辉, 司可. 基于改进RT-DETR的光伏板缺陷检测[J]. 广西师范大学学报（自然科学版）, 2026, 44(2): 52-64.
[7]	张胜伟, 曹洁. 融合傅里叶卷积与差异感知的钢材表面微小缺陷检测算法[J]. 广西师范大学学报（自然科学版）, 2026, 44(2): 90-102.
[8]	田晟, 赵凯龙, 苗佳霖. 基于改进YOLO11n模型的自动驾驶道路交通检测算法研究[J]. 广西师范大学学报（自然科学版）, 2026, 44(1): 1-9.
[9]	黄文杰, 罗维平, 陈镇南, 彭志祥, 丁梓豪. 基于YOLO11的轻量化PCB缺陷检测算法研究[J]. 广西师范大学学报（自然科学版）, 2026, 44(1): 56-67.
[10]	魏梓书, 陈志刚, 王衍学, 哈斯铁尔·马德提汗. 基于SBSI-YOLO11的轻量化轴承外观缺陷检测算法[J]. 广西师范大学学报（自然科学版）, 2025, 43(6): 80-91.
[11]	刘廷汉, 梁艳, 黄鹏升, 闭金杰, 黄守麟, 李廷会. 基于改进YOLOv8s的人脸痤疮小目标检测[J]. 广西师范大学学报（自然科学版）, 2025, 43(5): 114-129.
[12]	梁胤杰, 南新元, 蔡鑫, 李云鹏, 勾海光. 基于数据增广与改进YOLOv8的桥梁缺陷检测[J]. 广西师范大学学报（自然科学版）, 2025, 43(3): 84-97.
[13]	郭翔羽, 石天怡, 陈燕楠, 南新元, 蔡鑫. 基于YOLO-CDBW模型的列车接触网异物检测研究[J]. 广西师范大学学报（自然科学版）, 2025, 43(2): 56-69.
[14]	戴林华, 黎远松, 石睿, 何忠良, 李雷. HSED-YOLO:一种轻量化的带钢表面缺陷检测模型[J]. 广西师范大学学报（自然科学版）, 2025, 43(2): 95-106.
[15]	于雪松, 徐宝. 加权p、q对称损失函数下Burr分布参数的Bayes估计[J]. 广西师范大学学报（自然科学版）, 2024, 42(6): 186-193.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed